Ruihong Shen | 沈睿弘

  I am a sophomore in Zhi Class 2023 at the School of Electronics Engineering and Computer Science (EECS) of Peking University. I am pursuing a degree in Intelligence Science and Technology while also pursuing a dual degree in Psychology. I am currently advised by Prof. Yixin Zhu at Cognitive Reasnoning (CoRe) Lab, Institute for Artificial Intelligence, Peking University.
  My current research interest lies in physcial reasoning and few-shot learning, with the goal of enabling AI agents to understand our surrounding physical world. I'm also interested in the intersection of AI and cognitive science.
  Feel free to reach out if you have any comments, questions about me, my research, or anything else! 🥺

Email  /  Github /  Class WeChat Official Account

We present NFF, a modeling framework built on NODE that learns interpretable force field representations which can be efficiently integrated through an ODE solver to predict object trajectories. Unlike existing approaches that rely on high-dimensional latent spaces, NFF captures fundamental physical concepts such as gravity, support, and collision in an interpretable manner. Experiments on two challenging physical reasoning tasks demonstrate that NFF, trained with only a few examples, achieves strong generalization to unseen scenarios. This physics-grounded representation enables efficient forward-backward planning and rapid adaptation through interactive refinement.